2011 Volume 63 Issue 2 Pages 229-234
In this paper, a general algorithm for pedestrian detection by on-board monocular camera which can be applied to cameras of various view ranges in unified manner. The Spatio-Temporal MRF model extracts and tracks foreground objects as pedestrians and non-pedestrian distinguishing from background scenes as buildings by referring to motion difference. During the tracking sequences, cascaded HOG classifiers classify the foreground objects into the two classes of pedestrians and non-pedestrians. Finally, we get information about trajectory of pedestrians. We apply our methods to actual sequence, it perfume over 90% in detect rate and about 10% in false alarm rate.